Accession Number : ADA297984

Title :   Mid-Level Vision and Recognition of Non-Rigid Objects.

Descriptive Note : Technical rept.,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Subirana-Vilanova, J. B.

PDF Url : ADA297984

Report Date : JAN 1993

Pagination or Media Count : 241

Abstract : We address mid-level vision for the recognition of non-rigid objects. We align model and image using frame curves - which are object or "figure/ground" skeletons. Frame curves are computed, without discontinuities, using Curved Inertia Frames, a provably global scheme implemented on the Connection Machine, based on: non-cartisean networks; a definition of curved axis of inertia; and a ridge detector. I present evidence against frame alignment in human perception. This suggests: frame curves have a role in figure/ground segregation and in fuzzy boundaries; their outside/near/top/incoming regions are more salient; and that perception begins by selling a reference frame (prior to early vision), and proceeds by processing convex structures. (AN)

Descriptors :   *IMAGE PROCESSING, *PATTERN RECOGNITION, *COMPUTER VISION, MATHEMATICAL MODELS, ALGORITHMS, SIGNAL PROCESSING, OPTIMIZATION, TARGET RECOGNITION, SHAPE, PARALLEL PROCESSING, TARGET DISCRIMINATION, ALIGNMENT, BRIGHTNESS, CURVATURE, FRAMES, VISUAL PERCEPTION, TARGET DETECTION, DYNAMIC PROGRAMMING, IMAGE REGISTRATION, IMAGE MOTION COMPENSATION, CONTOURS.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE